© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111654
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reconc
    -0.25
    ISC
    -0.25
    kw
    -0.25
    clid
    -0.25
    ophil
    -0.24
    ght
    -0.24
    GBT
    -0.24
    ç¿Ĵ
    -0.24
    odiac
    -0.23
    NCY
    -0.23
    POSITIVE LOGITS
     Walton
    0.25
    æ¶Īè´¹åĵģ
    0.25
    æĭĨ
    0.24
    骨æŀ¶
    0.23
    èĪŀ
    0.23
    订éĺħ
    0.23
    OLE
    0.23
    èĮ¹
    0.23
    ritos
    0.23
    æĶ¯ä»ĺ
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.